© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 6868
    Prev
    Next
    INDEX
    Explanations

    technical details related to ability and functions associated with equipment or machinery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Prepositions followed by "the"

    np_acts-logits-general · gemini-2.0-flash

    prepositions followed by the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Abitanti
    -0.73
    oretical
    -0.63
     Mongols
    -0.59
    };*/
    -0.58
     IMC
    -0.58
     CJK
    -0.58
     ARD
    -0.58
    apunov
    -0.57
    iastes
    -0.56
     CTC
    -0.56
    POSITIVE LOGITS
     the
    2.79
    The
    0.96
     The
    0.94
    the
    0.89
    <bos>
    0.80
     själva
    0.73
    enthe
    0.73
    rethe
    0.69
    nthe
    0.65
     את
    0.62
    Activations Density 8.131%

    No Known Activations